|Publication number||US6622260 B1|
|Application number||US 09/475,417|
|Publication date||Sep 16, 2003|
|Filing date||Dec 30, 1999|
|Priority date||Dec 30, 1999|
|Also published as||DE10085281T0, DE10085281T1, US7904751, US20040019835, WO2001050262A1|
|Publication number||09475417, 475417, US 6622260 B1, US 6622260B1, US-B1-6622260, US6622260 B1, US6622260B1|
|Inventors||Suresh Marisetty, Mani Ayyar, Nhon T. Quach, Bernard J. Lint|
|Original Assignee||Suresh Marisetty, Mani Ayyar, Nhon T. Quach, Bernard J. Lint|
|Export Citation||BiBTeX, EndNote, RefMan|
|Patent Citations (28), Referenced by (86), Classifications (8), Legal Events (4)|
|External Links: USPTO, USPTO Assignment, Espacenet|
This invention relates generally to processor systems, and more particularly to cooperative error handling in processor systems.
An important element in creating a highly reliable computing system is the handling of errors such as hard errors and soft errors. Soft errors occur when alpha particles or cosmic rays strike an integrated circuit and alter the charges stored on the voltage nodes of the circuit. If the charge alteration is sufficiently large, a voltage representing one logic state may be changed to a voltage representing a different logical state. For example, a voltage representing a logic true state may be altered to a voltage representing a logic false state and any data that incorporates the logic state may be corrupted. This is also referred to as data corruption.
Soft error rates (SERs) for integrated circuits, such as microprocessors (“processors”) increase as semiconductor process technologies scale to smaller dimensions and lower operating voltages. Smaller process dimensions allow greater device densities to be achieved on the processor die. This greater density increases the likelihood that an alpha particle or cosmic ray will strike one of the processor's voltage nodes. Lower operating voltages mean that smaller charge disruptions may alter the logic states represented by the node voltages. Both trends point to higher SERs in the future. Consequently, soft errors should be handled appropriately to avoid data corruption and other errors that may caused by soft errors.
Hard errors occur when components or devices in a computer system malfunction. Components or devices in a computer system can be damaged a number of ways such as by voltage fluctuations, power surges, lightning and heat. If these hard errors are not discovered and corrected, data corruption along with a complete system failure is likely.
The process of error handling consists of error detection and error recovery. Error detection is typically accomplished in the processor or system logic hardware through the addition of parity check bits in the memory arrays, buses and data paths.
Error recovery may include error containment and system availability. Error containment and system availability often conflict with each other. Error containment is preventing an error from propagating to other computer devices, components or system logic. System logic is the portion of the logic in a computer system that enables the processor, memory and input/output (IO) devices to work together.
Computer systems often reboot in an attempt to contain errors. While rebooting, the computer system is not available. Frequent rebooting of personal computers may be somewhat acceptable even though it is highly annoying. However, frequent rebooting of high availability systems, such as system servers, is not acceptable. System servers, such as mail servers and network servers, are generally relied on to run critical applications in a non-stop fashion.
Another consideration in error recovery is the error recovery time. The error recovery time is the time it takes for error recovery to be completed. While error recovery is being performed, operating systems lose control of the computer system. Many modern operating systems, such as Windows NT and Unix, cannot tolerate a loss of control of the system for a significant time while the system is going through error recovery.
Multiple processor (MP) computer systems further complicate the problems of error recovery and error recovery time. In MP computer systems, different processors are executing different processes. One or more of the processors may encounter the error but all of the processors can be affected. Generally, MP computer systems lack a coordinated approach to error recovery. This lack of an appropriate error handling can cause MP computer systems to reboot unnecessarily and data to be corrupted.
Additionally, error handling of today provides only limited error information without any specific format. In many cases, error handling of today provides no error information. Forcing a computer system to reboot is bad enough, but having your computer reboot without obtaining information about the error that caused your computer to reboot is even worse.
Not all errors encountered in a computer system can be recovered from. However, current error handling fails to provide enough error information.
For the reasons stated above, and for other reasons stated below which will become apparent to those skilled in the art upon reading and understanding the present specification, there is a need in the art for a computer system that handles errors in a coordinated manner.
The present invention provides systems and methods for error handling on processor systems. The systems and methods may be utilized for single or multiple processor computer systems to handle errors in a coordinated manner.
One embodiment of the invention is a computer system including a non volatile memory and at least one processor. A firmware error handling routine is stored on the non volatile memory. The firmware error handling routine is for handling errors. Each of the at least one processors detects errors. Each processor executes the firmware error handling routine on detecting an error. The executed firmware error handling routine handles the error. The executed firmware error handling routine also logs error information to a log. The firmware also coordinates the error handling with other software layers like the Operating System.
Other embodiments of systems and methods for error handling are disclosed.
FIG. 1 illustrates errors that may occur in a computer system;
FIG. 2 illustrates a system for error handling according to one embodiment of the present invention;
FIG. 3 illustrates a system for error handling according to one embodiment of the present invention;
FIG. 4 illustrates a method for handling errors according to one embodiment of the present invention; and
FIG. 5 illustrates a computer system suitable for implementing the present invention.
The following discussion sets forth numerous specific details to provide a thorough understanding of the invention. However, those of ordinary skill in the art, having benefit of this disclosure, will appreciate that the invention may be practiced without these specific details. In addition, various well known methods, procedures, components, and circuits have not been described in detail in order to focus attention on the features of the present invention.
As stated above, error handling in computer systems involve error detection and error recovery. In error recovery, errors should be contained and computer systems should be highly available. Computer systems utilizing error handling that is coordinated among processors, system logic hardware, firmware and operating system can contain errors and reduce the time computer systems are not available. Additionally, the processor(s), system logic hardware, firmware and operating system should have interfaces to one another to allow coordination between them during error handling.
System software is defined herein as the firmware and operating system (OS) that is executed by a single CPU in a single processor system, or is executed by a plurality of CPUs in a multi-processor system.
Firmware as used herein refers to processor routines that are stored in non-volatile memory structures such as read only memories (ROMs), flash memories, and the like. These memory structures preserve the code stored in them even when power is shut off. Even though firmware is stored in non-volatile memory, firmware may be copied or shadowed to volatile memory. Typically, this is done for performance reasons. One of the principal uses of traditional firmware is to provide necessary instructions or routines that control a computer system when it is powered up from a shut down state, before volatile memory structures have been tested and configured. Firmware routines may also be used to reinitialize or reconfigure the computer system following various hardware events and to handle certain platform events like system interrupts.
For one embodiment, firmware includes two major components, the processor abstraction layer (PAL) and the system abstraction layer (SAL). The PAL encapsulates all processor model specific hardware. The PAL provides a consistent software interface to access the processor resources across different processor implementations. SAL is a platform specific firmware component that is typically provided by original equipment manufacturers (OEM) and BIOS vendors. The SAL is a firmware layer that isolates an operating system and other higher level software from implementation differences in the platform. Both the PAL and SAL, provide system initialization and boot strapping, machine check abort (MCA) handling, platform management interrupt handling, and other processor and system functions which vary across different implementations.
Operating systems (OS) interact with firmware to provide an environment in which applications can be executed by the CPU. By utilizing firmware, an OS can be designed to run on many different processing systems without re-writing the OS for each variation in platforms.
A machine check abort (MCA) is a hardware event or signal that indicates that a hardware error or error has occurred that threatens to damage the architectural state of the machine and may possibly cause data corruption. A corrected machine check (CMC) is a signal or event that indicates that an error has been successfully corrected by hardware and/or software.
There are two types of MCAs, local and global. A local MCA is detected and handled by a single processor of a multiple processor (MP) computer system. The local MCA is invisible to other processors in the MP computer system. A global MCA may be detected by one or more processors, but is visible to all processors in the MP computer system.
For a single processor system, there are only local MCAs. The MCAs in the single processor computer system are not divided between global and local since there are not other processors in the computer system.
Additionally, there are two types of logs, MCA and CMC logs. MCA logs are for errors that have not yet been corrected and are used during error recovery to store information about the error and the ongoing error recovery process. CMC logs are for errors that have been corrected. CMC logs contain information about the error that occurred and may include information on how it was corrected. CMC logs may be converted from MCA logs when an error is corrected.
For one embodiment, errors that occur in a computer system can be divided into soft errors and hard errors. Generally, software errors involve faulty data and may be fixed by writing over the faulty data. Software errors may be triggered by alpha particles and cosmic rays and may be detected by parity checking or ECC. Hard errors are defects or malfunctions in any piece of hardware or component in the computer system, such as the platform hardware or processors.
FIG. 1 shows some of the types of errors that may occur in a computer system and the severity.
The first category of errors are errors that can be corrected by the processor that encountered the error 101 without using PAL, SAL, or OS. This error type is sometimes called as “continuable error with hardware correction”. This is the least severe error of FIG. 1. The processor can correct this error and continue executing its current process without any impact on its current course. In a multi processor environment, these types of errors do not require shutting down any of the processors. An example of this type of error is a single bit ECC (error correcting code) error in a processor cache that is corrected by platform chipset hardware. Generally, a CMC signal or event is sent to the firmware and operating system to inform the firmware and operating system that an error has occurred and has been corrected.
The second category of errors are errors correctable using error handling routines in PAL 101, SAL 102, and OS 103 and is shown at 102. This error type is sometimes called “continuable error with firmware correction”. Typically, any processes executing on a detecting processor are interrupted and information necessary to resume the these processes is stored in a log. The error handling routines in these layers can be used to correct the error and the processes can resume execution. The resumed processes are unaware of the error or the interruption. An example of this type of error is a parity error in the processor instruction cache. In this case, firmware will invalidate the entire instruction cache, access another copy of the instruction, and resume execution of the interrupted process. This type of error can be signaled to a processor by the platform via a double bit ECC error on the system bus.
The third category of errors are errors that cannot be completely corrected by either the processors or firmware (PAL and SAL) and the offending process needs to be terminated to achieve error containment and is shown at 103. This error type is sometimes called a “recoverable error”. These errors are corrected by the error handling routine of an OS. An example of this type of error is a parity error in a first level data cache. When this error is detected, the processor cannot prevent the register file from being updated with the bad data. In this case, the firmware will flush the entire first level data cache and the offending process is terminated by the error handling routine of the OS if it is a non-critical user or kernel process. If the process is critical, a reboot or halt of the system is typically performed.
The fourth category of errors are errors that can not be corrected by the processors, platform hardware, PAL, SAL, and OS and is shown at 104. This type of error is referred to as a “non-recoverable error”. For these errors, the system may need a reboot or halt and execution can not continue. An example of this type of error is a parity error on any access to a dirty line in a processor cache. In a multi-processor environment, a global MCA signal is generated and sent to processors other than the detecting processor.
FIG. 2 illustrates one embodiment of a system for coordinated error handling. The system includes a PAL 201, SAL 202, OS 203, at least one processor 204, and platform hardware 205. The system is not limited to operating only at boot time and operates during run time. The PAL 201 and SAL 202 are together known as firmware. The code for these layers may reside in a non-volatile memory or persistent memory of the system such as flash read only memory (ROM). The code for these layers may be shadowed to other memory devices. In the following discussion, it is intended that the terms PAL, SAL, and OS represent PAL, SAL, or OS code intended to be executed by a processor.
PAL 201 includes a set of procedures and an error handling routine. The set of procedures access processor hardware, and can encapsulate processor model specific hardware. This set of procedures may be called by other system software or hardware. By providing the set of procedures, PAL 201 provides a consistent interface to access processor resources across different processor implementations. The error handling routine of PAL 201 is also known as PAL_CHECK. Error handling for an error may be handed off to the error handling routine of PAL 201 or PAL_CHECK.
SAL 202 includes an error handling routine. The error handling routine is also known as SAL_CHECK. The error handling routine may be handed off to from the error handling routine of PAL 201 or from PAL_CHECK to SAL_CHECK.
OS 203 also includes an error handling routine. The error handling routine may be handed off to from the error handling routine of SAL 202. The error handling routine of OS 203 is a machine check component of OS 203 also known as OS_MCA.
Processor 204 can represent one or more processors in a single or multiple processor (MP) computer system and is not limited to a certain processor. The platform hardware 205 includes hardware typically used in computer systems including, but not limited to, off chip caches, buses, buffers, memory, system logic and peripheral devices.
On processor 204 detecting an error, a machine check abort (MCA) is generated. A machine check abort (MCA) is a hardware event or signal that indicates that a hardware error or error has occurred that threatens to damage the architectural state of the machine and may possibly cause data corruption.
The detecting processor attempts to correct the error. If the detecting processor is able to correct the error, a correctable machine check interrupt (CMCI) or other CMC signal is generated. If the detecting processor is unable to correct the error, the detecting processor executes the error handling routine of PAL 201 thereby handing off to the error handling routine of PAL 201.
The error handling routine of PAL 201 determines if errors are processor related, saves minimal state information and corrects errors where possible. The minimal state information may be saved to a log or log register and contains sufficient information for another layer such as SAL 202 to understand the error at a global level and to potentially resume interrupted processes. Additionally, the PAL 201 error handling routine attempts to contain the error and correct the error. Error containment simply means keeping the error within boundaries and preventing the error from propagating to other processors or networks. One example of containing and correcting an error is that a corrupted instruction cache line can be removed and the cache line marked unusable. If the error handling routine succeeds at recovering from the error, a CMCI may be generated. Once the error handling routine of PAL 201 has completed handling the error, execution branches to or is handed off to the error handling routine of SAL 202. When execution is handed off to the error handling routine of SAL 202, minimal state information and error status is passed to the error handling routine of SAL 202.
The error handling routine of SAL 202 determines whether it has enough information to process or handle the error. If the error handling routine determines that more information is needed, the error handling routine of SAL 202 may call the set of PAL 201 procedures to obtain additional state information about the processor and the error. Additionally, the error handling routine logs information about the error to a log. The error handling routine attempts to correct the error. If the error remains uncorrected, the error handling routine of SAL 202 analyzes the state information and the type of error received from PAL 201 and determines the severity of the error as being either continuable, recoverable, or non-recoverable. Additionally, the error handling routine may compare the errors to other errors that have occurred and have not yet corrected. In the event that multiple errors have occurred, the error handling routine of SAL 202 prioritizes which errors are to be handled first corresponding to the severity of the error.
For errors which have the characteristic of being severe and global or when several errors occur within a short amount of time, the error handling routine of SAL 202 causes the computer system to enter a rendezvous state to handle the error. In the rendezvous state, all processors in the computer system except for one enter an idle state. The one processor, also known as a monarch processor, takes over error handling. The monarch processor performs error handling at the system level and accumulates all the error logs. The monarch processor may access procedures and routines from PAL 201, SAL 202 and OS 203.
The log that the error handling routine of SAL 202 generates is in a predetermined format and may be accessed by the OS 203 or other diagnostic software. The error handling routine of SAL 202 logs processor and platform error information, saves processor and platform state information, performs hardware specific corrections, clears the error log and re-enables future information collection, halts the processor or platform as necessary, and handles multi processor situations. The processor and platform error information is logged in either a CMC log or MCA log. The error handling routine of SAL 202 can use the PAL 201 set of procedures to obtain additional information from the processor or platform. CMC logs store information about errors corrected by hardware or firmware. For corrected errors, intervention by the OS 203 is not required for error handling, only PAL and SAL will do most of the work and return back to the interrupted processes, but OS 203 can be notified of the corrected error through a low priority corrected machine check (CMC) signal or event. The system software can generate the CMC event by polling for a flag or by programming the hardware to generate an interrupt.
For errors which are not corrected by the error handling routine of SAL 202, execution branches or hands off from the error handling routine of SAL 202 to the error handling routine of OS 203.
The error handling routine of OS 203 retrieves the logs and state information from SAL 202. The error handling routine performs correction on operating system controlled hardware resources. Further, the error handling routine checks the state information to see if processing can continue if the error is corrected. For example, if PAL 201 did not get all the state information, the system may be unable to continue processing even if the error is corrected. If the error handling routine of OS 203 corrects the error, processor execution branches to the error handling routine of SAL 202 with the status of the corrected error. Also, the error handling routine of OS 203 can call the set of PAL procedures to return to an interrupted process, jump to the interrupted context or set a new context. If the error remains uncorrected, control of execution returns to the error handling routine of SAL 202 with an uncorrected status value and an indication for the error handling routine of SAL 202 to halt or reboot the system.
FIG. 3 illustrates one embodiment of a system for error handling. The system includes at least one processor 304(1)-304(j) (collectively 304), at least one platform hardware 305(1)-305(j) (collectively 305), a processor abstraction layer (PAL) 301(1)-301(j) (collectively 301), a system abstraction layer (SAL) 302 and an operating system (OS) 303.
The processor 304 and platform hardware 305 can detect errors and attempt to correct them. Errors that affect only one processor are local errors. Errors that effect more than one error are global errors. If the processor 304 is unable to correct the error, error handling is handed off to PAL 301. On detecting an interrupt, a signal or interrupt is generated to allow other system software to be aware of the error.
Each PAL 301 is coupled to a corresponding processor and platform hardware. PAL 301 provides a consistent software interface to access the processor resources across different processor implementations. The software interface may be utilized by other software in the system including the OS 303 and hardware such as the one or more processors 304 and the at least one platform hardware 305. For software layers above PAL 301, the software interface is in the form of an API. API calls always return back to the caller.
PAL 301 includes an error handling routine that, when executed by a processor, performs error handling. Control of error handling is handed off to the PAL error handling routine if the processor 304 was unable to correct a detected error. The PAL error handling routine attempts to correct the error or recover from the error. When the PAL error handling routine has finished its processing of the error, control of error handling hands off to SAL 302. Additionally, the PAL error handling routine passes error information to SAL 302. The error information can include information such as error type, error status (corrected or uncorrected) and information related to the error. The “hand off” is a unidirection transfer of control.
SAL 302 is a platform specific firmware component that is typically provided by original equipment manufacturers (OEM) and BIOS vendors. The SAL is a firmware layer that isolates an operating system and other higher level software from implementation differences in the platform. There is a PAL-SAL software interface that allows communication between these PAL and SAL layers. The PAL-SAL interface is of a predetermined and standardized format. SAL 302 includes an error handling routine that, when executed by a processor, performs error handling. The SAL error handling routine is branched to once the PAL error handling routine has finished processing the error or attempting to correct the error. The SAL error handling routine checks the status of the error. If the error is uncorrected, the SAL error handling routine determines the severity of the error, creates a log regarding the error or adds information regarding the error to a log and attempts to correct the error. The severity of the error is determined by using the PAL error information. The SAL error handling routine may use PAL procedures or PAL APIs to gain additional information about the error in order to determine the severity of the error. If the error is corrected, the SAL error handling routine creates a log regarding the error or adds information regarding the error to an existing log.
SAL 302 generates a system log 306 for storing information about errors. The system log may include a processor log and a platform log. The processor log contains log information pertaining to the processor. In a multiprocessor environment, the processor log contains information pertaining to the processor on which a call for state information is executed. The platform log contains information pertaining to the entire platform. Since multiple errors are possible, the error log information is structured in the form of a linked list of error log structures with each entry describing one error.
The information contained in the log is implementation dependent. However, the log will generally include a time stamp, validation bits, cache status, TLB check info, and system bus information, and platform specific information for memory and I/O errors.
SAL 303 includes a GET_INFO procedure or API for getting state information. The procedure provides a programmatic interface to processor and platform information logged by SAL 302 with respect to the machine state at the time of errors including MCAs and CMCs. The procedure may be called by the OS 303 or any other diagnostic software. The procedure provides a standardized format for accessing logged information. The amount of state information saved by SAL is implementation dependent. SAL 302 can provide an indication of what information SAL is logging. This may be done, for example, by providing validation bits indicating the saved state information. The procedure may clear the log if instructed to do so by the calling OS 303 or other diagnostic software. The log may be stored in a register. The log is generally cleared on booting the system. In the case of multiple errors of the same type, the log will provide details and information relating to the first occurring error. The call may specify whether it is requesting a platform log or processor log. The procedure can write the log information to a region of memory specified by the calling software.
The system log 306 may be used by other software layers and applications. These layers and applications may inform a user of errors that have occurred, data that has been damaged, or parts that need to be replaced.
Once the SAL 302 error handling routine has finished processing the error, error handling branches or is handed off to the OS 303 if the SAL error handling routine was not able to correct the error.
On some types of errors, the SAL or PAL error handling routine forces the computer system to enter a rendezvous state in order to attempt error recovery. In the rendezvous state, only one of the at least one processors and its corresponding PAL and platform hardware are operational. The one processor is called a monarch processor. The other processors are in an idle state. The monarch processor performs the error handling. The rendezvous state is often used for global errors.
The OS 303 interacts with the PAL 301 and SAL 302 to provide an environment in which applications may be run. The OS 303 interacts with PAL 301 and SAL 302 by using as OS-PAL and OS-SAL software interfaces. The OS-PAL and OS-SAL have a predetermined format. The OS-PAL interface is an interface between the OS 303 and PAL 301. The OS-SAL interface is an interface between the OS 303 and SAL 302. The OS 303, like SAL 302, is system wide. The OS 303 includes an error handling routine that, when executed by a processor, performs error handling including error recovery. The OS 303 error handling routine is passed some information from the SAL error handling routine. The OS 303 may utilize PAL 301 procedures to obtain additional information about the error. Further, the OS error handling routine may access the system log 306 created by SAL 302 by utilizing the SAL 302 API. The OS 303 may cause processes to be interrupted. The OS 303 may tell the user to replace a certain system component that caused the error. If the OS 303 is unable to correct the error, the OS may require that the system be halted or rebooted.
FIG. 4 shows a flow chart of one embodiment for cooperative error handling in a computer system. The system hardware detects an error at 401 and generates a hardware event or signal known as a machine check. The system hardware can include but is not limited to at least one processor, a chipset, buffers, off-chip caches, buses, peripheral devices and other devices.
The system hardware attempts to correct the error at 402. The system hardware may have some built in mechanism to correct certain errors or the system hardware may access routines in firmware to correct the error. If the error is corrected 403, processing of the system continues without having interrupted any processes. A signal or interrupt may be sent to an operating system and firmware to notify the firmware and operating system that an error has occurred and been corrected. An example of a type of error that is correctable by the system hardware is a single bit error in a processor cache that is corrected by processor hardware.
If the system hardware is unable to correct the error, control of error handling passes to a PAL error handling routine at 404. The PAL error handling routine is executed on a processor, usually the detecting processor, of the system hardware. The error handling routine attempts to correct the error at 404. The PAL error handling routine may also create a log containing state information and error status.
If PAL corrects the error, SAL generates or creates a log of the error. SAL saves or logs information about the error and how it was corrected to the log. If PAL fails to correct the error, SAL attempts to correct the error at 407. SAL may access PAL procedures to attempt to correct the error. Additionally, SAL determines the severity of the error by analyzing the error and the state information. SAL may determine that the error is so severe that it can not be corrected and recoverable. For these uncorrectable or unrecoverable errors SAL causes the computer system to halt or reboot. Additionally, SAL generates or creates a log of the error regardless of whether the error has been corrected 408. SAL may log information such as the error type and error status. Additionally, SAL logs state information.
If the firmware was not able to correct the error 409, the OS attempts to correct the error 411. The OS determines if any processes need to be interrupted. The OS also determines whether normal execution can continue even if the error si corrected. In some instances, it may be necessary to reboot even if the OS is able to correct the error. In other instances, the OS can only report the error and cause the system to halt. If the error is corrected 412, normal processing is resumed and error handling ends at 410. If the error is not corrected 412, the computer system is rebooted or halted at 413.
An example of the error that may be corrected by the OS is a parity error in a data cache resulting in faulty data. The OS may terminate the process that created or used the data in the data cache. An example of an error that may not be corrected by the OS is a parity error in a portion of system memory where critical portions of the operating system are located. Those portions can not be expected to perform reliably and the system should be halted or rebooted to prevent further errors.
FIG. 5 is a block diagram of one embodiment of a computer system 500 that is suitable for implementing the present invention. The disclosed embodiment of computer system 500 includes one or more processors 510 that are coupled to system logic 530 through a processor bus 520. A system memory 540 is coupled to system logic 520 through bus 550. A non-volatile memory 570 and one or more peripheral devices 580(1)-580(j) (collectively, devices 580) are coupled to system logic 530 through peripheral bus 560. Peripheral bus 560 represents, for example, one or more peripheral component interconnect (PCI) buses, industry standard architecture (ISA) buses, extended ISA (EISA) buses, and comparable peripheral buses. Non-volatile memory 570 may be a static memory device such as a read only memory (ROM) or flash memory. Peripheral devices 580 include, for example, a keyboard, mouse or other pointing devices, mass storage devices such as hard drives and digital video discs (DVD), a display, and the like. These devices, together with system logic 530 define the computing platform for system 500.
For the disclosed embodiment of system 500, the at least one processor 510 may execute code or routines stored in system memory 540. The code for the operating system (OS) is in the system memory 540. The processor also executes code from the non-volatile memory 570. The firmware including PAL and SAL can be located in the non-volatile memory.
The various embodiments described above and other variations permit better error handling in computer systems cooperatively handling errors. These embodiments can extend to networked systems or distributed systems. By handling errors better, other software can be developed with less regard for possible errors. Errors propagated from other errors can be reduced in number because errors can be handled before encountered by other processors. Software developers can focus more on features and new developments for their products with the resources saved by better error handling in the system. Computer users can notice improved performances in systems, less system shutdowns and reboots, less data loss from unexpected shutdowns and time saved by having a computer system that is more stable.
Although specific embodiments have been illustrated and described herein, it will be appreciated by those of ordinary skill in the art that any arrangement which is calculated to achieve the same purpose may be substituted for the specific embodiments shown. This application is intended to cover any adaptations or variations of the present invention. Therefor, it is manifestly intended that this invention be limited only by the following claims and equivalents thereof.
|Cited Patent||Filing date||Publication date||Applicant||Title|
|US4317010 *||Dec 26, 1979||Feb 23, 1982||Fillot Jean Jacques Y||Remote monitoring system for remote locating and gain regulating of amplification circuits in data transmission line|
|US5056091 *||Mar 15, 1990||Oct 8, 1991||Hewlett-Packard Company||Method for handling errors detected in a computer system|
|US5107500 *||Apr 19, 1989||Apr 21, 1992||Fujitsu Ltd.||Diagnostic expert system|
|US5245615 *||Jun 6, 1991||Sep 14, 1993||International Business Machines Corporation||Diagnostic system and interface for a personal computer|
|US5313625 *||Jul 30, 1991||May 17, 1994||Honeywell Inc.||Fault recoverable computer system|
|US5481707 *||Apr 11, 1995||Jan 2, 1996||Unisys Corporation||Dedicated processor for task I/O and memory management|
|US5594861 *||Aug 18, 1995||Jan 14, 1997||Telefonaktiebolaget L M Ericsson||Method and apparatus for handling processing errors in telecommunications exchanges|
|US5619644 *||Sep 18, 1995||Apr 8, 1997||International Business Machines Corporation||Software directed microcode state save for distributed storage controller|
|US5673386||Jan 11, 1996||Sep 30, 1997||U S West Technologies, Inc.||Method and system for identification of software application faults|
|US5699505 *||Aug 20, 1996||Dec 16, 1997||Unisys Corporation||Method and system for automatically collecting diagnostic information from a computer system|
|US5717850 *||Mar 12, 1996||Feb 10, 1998||International Business Machines Corporation||Efficient system for predicting and processing storage subsystem failure|
|US5740357||Oct 26, 1994||Apr 14, 1998||Digital Equipment Corporation||Generic fault management of a computer system|
|US5784547 *||Mar 18, 1996||Jul 21, 1998||Abb Patent Gmbh||Method for fault-tolerant communication under strictly real-time conditions|
|US5941996 *||Jul 25, 1997||Aug 24, 1999||Merrill Lynch & Company, Incorporated||Distributed network agents|
|US5948107 *||May 28, 1997||Sep 7, 1999||Intel Corporation||Method of handling errors in complex inheritance hierarchies|
|US5956480 *||Aug 18, 1994||Sep 21, 1999||Fujitsu Limited||Terminal and online system for tracking version of data and program|
|US5958049 *||Mar 17, 1997||Sep 28, 1999||International Business Machines Corporation||Operating system debugger using kernel and dynamic extension with debugger drivers to support different output devices|
|US5991518 *||Jan 28, 1997||Nov 23, 1999||Tandem Computers Incorporated||Method and apparatus for split-brain avoidance in a multi-processor system|
|US6058490 *||Apr 21, 1998||May 2, 2000||Lucent Technologies, Inc.||Method and apparatus for providing scaleable levels of application availability|
|US6061810 *||Dec 5, 1996||May 9, 2000||Compaq Computer Corporation||Computer system with error handling before reset|
|US6065139 *||Mar 31, 1997||May 16, 2000||International Business Machines Corporation||Method and system for surveillance of computer system operations|
|US6170067 *||Oct 1, 1997||Jan 2, 2001||Micron Technology, Inc.||System for automatically reporting a system failure in a server|
|US6173386 *||Dec 14, 1998||Jan 9, 2001||Cisco Technology, Inc.||Parallel processor with debug capability|
|US6381694 *||Feb 18, 1994||Apr 30, 2002||Apple Computer, Inc.||System for automatic recovery from software problems that cause computer failure|
|US6408407 *||Jun 3, 1999||Jun 18, 2002||Ncr Corporation||Methods and apparatus for delegated error handling|
|US6438709 *||Dec 29, 1997||Aug 20, 2002||Intel Corporation||Method for recovering from computer system lockup condition|
|EP0730230A2||Mar 1, 1996||Sep 4, 1996||Hal Computer Systems, Inc.||Method and apparatus for prioritizing and handling errors in a computer system|
|EP0953911A2||Apr 13, 1999||Nov 3, 1999||Lucent Technologies Inc.||Method and apparatus for providing scaleable levels of application availability|
|Citing Patent||Filing date||Publication date||Applicant||Title|
|US6915460 *||Jun 26, 2001||Jul 5, 2005||International Business Machines Corporation||Method, apparatus, and program for service processor surveillance with multiple partitions|
|US7103639 *||Dec 5, 2000||Sep 5, 2006||Hewlett-Packard Development Company, L.P.||Method and apparatus for processing unit synchronization for scalable parallel processing|
|US7136793 *||Jan 14, 2003||Nov 14, 2006||Lockheed Martin Corporation||System and method for modeling a propagation and containment process|
|US7243264 *||Nov 1, 2002||Jul 10, 2007||Sonics, Inc.||Method and apparatus for error handling in networks|
|US7251755 *||Feb 13, 2004||Jul 31, 2007||Intel Corporation||Apparatus and method for maintaining data integrity following parity error detection|
|US7373558||Sep 23, 2004||May 13, 2008||Intel Corporation||Vectoring process-kill errors to an application program|
|US7380169 *||Sep 24, 2004||May 27, 2008||Intel Corporation||Converting merge buffer system-kill errors to process-kill errors|
|US7418557||Nov 30, 2004||Aug 26, 2008||International Business Machines Corporation||Managing multiprocessor operations|
|US7533300 *||Feb 13, 2006||May 12, 2009||Intel Corporation||Configurable error handling apparatus and methods to operate the same|
|US7546489 *||Jan 25, 2005||Jun 9, 2009||Seagate Technology Llc||Real time event logging and analysis in a software system|
|US7584388 *||Jul 18, 2005||Sep 1, 2009||Fujitsu Limited||Error notification method and information processing apparatus|
|US7650467||Jan 19, 2010||International Business Machines Corporation||Coordination of multiprocessor operations with shared resources|
|US7653008||Jan 26, 2010||Bea Systems, Inc.||Dynamically configurable service oriented architecture|
|US7653808 *||Nov 27, 2002||Jan 26, 2010||Intel Corporation||Providing selectable processor abstraction layer components within one BIOS program|
|US7716520 *||Jul 17, 2007||May 11, 2010||Fujitsu Limited||Multi-CPU computer and method of restarting system|
|US7721148||Jun 29, 2006||May 18, 2010||Intel Corporation||Method and apparatus for redirection of machine check interrupts in multithreaded systems|
|US7904751 *||Mar 8, 2011||Intel Corporation||System abstraction layer, processor abstraction layer, and operating system error handling|
|US7953907 *||May 31, 2011||Marvell International Ltd.||Concurrent input/output control and integrated error management in FIFO|
|US8024604 *||Sep 20, 2011||Fujitsu Limited||Information processing apparatus and error processing|
|US8095831 *||Jan 10, 2012||Freescale Semiconductor, Inc.||Programmable error actions for a cache in a data processing system|
|US8185916||May 22, 2012||Oracle International Corporation||System and method for integrating a business process management system with an enterprise service bus|
|US8214830 *||Jul 3, 2012||Intel Corporation||Performance in a virtualization architecture with a processor abstraction layer|
|US8250404||Aug 21, 2012||International Business Machines Corporation||Process integrity of work items in a multiple processor system|
|US8271701||Sep 18, 2012||Marvell International Ltd.||Concurrent input/output control and integrated error management in FIFO|
|US8677205 *||Mar 10, 2011||Mar 18, 2014||Freescale Semiconductor, Inc.||Hierarchical error correction for large memories|
|US8713350||Dec 8, 2009||Apr 29, 2014||Hewlett-Packard Development Company, L.P.||Handling errors in a data processing system|
|US8839032||Dec 8, 2009||Sep 16, 2014||Hewlett-Packard Development Company, L.P.||Managing errors in a data processing system|
|US8914712||Feb 27, 2012||Dec 16, 2014||Freescale Semiconductor, Inc.||Hierarchical error correction|
|US8949468||Oct 11, 2005||Feb 3, 2015||International Business Machines Corporation||Method and system for time synchronization among systems using parallel sysplex links|
|US8996394||Nov 8, 2007||Mar 31, 2015||Oracle International Corporation||System and method for enabling decision activities in a process management and design environment|
|US9298523||Sep 22, 2014||Mar 29, 2016||International Business Machines Corporation||Method and system for time synchronization among systems using parallel sysplex links|
|US20020069270 *||Dec 5, 2000||Jun 6, 2002||Walton Andrew C.||Method and apparatus for processing unit synchronization for scalable parallel processing|
|US20020199138 *||Jun 26, 2001||Dec 26, 2002||International Business Machines Corporation||Method, apparatus, and program for service processor surveillance with multiple partitions|
|US20040019835 *||Jul 28, 2003||Jan 29, 2004||Intel Corporation||System abstraction layer, processor abstraction layer, and operating system error handling|
|US20040088607 *||Nov 1, 2002||May 6, 2004||Wolf-Dietrich Weber||Method and apparatus for error handling in networks|
|US20040103273 *||Nov 27, 2002||May 27, 2004||Goud Gundrala D.||Delaying the authentication of a processor abstraction layer component|
|US20040138863 *||Jan 14, 2003||Jul 15, 2004||Simkins David Judson||System and method for modeling a propagation and containment process|
|US20040181731 *||Jan 16, 2004||Sep 16, 2004||Advantest Corporation||Semiconductor test system storing pin calibration data, commands and other data in non-volatile memory|
|US20050068888 *||Sep 26, 2003||Mar 31, 2005||Komarla Eshwari P.||Seamless balde failover in platform firmware|
|US20050193288 *||Feb 13, 2004||Sep 1, 2005||Joshi Aniruddha P.||Apparatus and method for maintaining data integrity following parity error detection|
|US20050264581 *||May 18, 2005||Dec 1, 2005||Bea Systems, Inc.||Dynamic program modification|
|US20050267892 *||May 18, 2005||Dec 1, 2005||Patrick Paul B||Service proxy definition|
|US20050267947 *||May 18, 2005||Dec 1, 2005||Bea Systems, Inc.||Service oriented architecture with message processing pipelines|
|US20050270970 *||May 19, 2005||Dec 8, 2005||Bea Systems, Inc.||Failsafe service oriented architecture|
|US20050273497 *||May 19, 2005||Dec 8, 2005||Bea Systems, Inc.||Service oriented architecture with electronic mail transport protocol|
|US20050273502 *||May 19, 2005||Dec 8, 2005||Patrick Paul B||Service oriented architecture with message processing stages|
|US20050273516 *||May 18, 2005||Dec 8, 2005||Bea Systems, Inc.||Dynamic routing in a service oriented architecture|
|US20050273517 *||May 18, 2005||Dec 8, 2005||Bea Systems, Inc.||Service oriented architecture with credential management|
|US20050273520 *||May 19, 2005||Dec 8, 2005||Bea Systems, Inc.||Service oriented architecture with file transport protocol|
|US20050278335 *||May 18, 2005||Dec 15, 2005||Bea Systems, Inc.||Service oriented architecture with alerts|
|US20050278374 *||May 18, 2005||Dec 15, 2005||Bea Systems, Inc.||Dynamic program modification|
|US20060005063 *||May 18, 2005||Jan 5, 2006||Bea Systems, Inc.||Error handling for a service oriented architecture|
|US20060007918 *||May 19, 2005||Jan 12, 2006||Bea Systems, Inc.||Scaleable service oriented architecture|
|US20060031353 *||May 18, 2005||Feb 9, 2006||Bea Systems, Inc.||Dynamic publishing in a service oriented architecture|
|US20060031354 *||May 19, 2005||Feb 9, 2006||Bea Systems, Inc.||Service oriented architecture|
|US20060031355 *||May 19, 2005||Feb 9, 2006||Bea Systems, Inc.||Programmable service oriented architecture|
|US20060031432 *||May 19, 2005||Feb 9, 2006||Bea Systens, Inc.||Service oriented architecture with message processing pipelines|
|US20060031433 *||May 19, 2005||Feb 9, 2006||Bea Systems, Inc.||Batch updating for a service oriented architecture|
|US20060031481 *||May 18, 2005||Feb 9, 2006||Bea Systems, Inc.||Service oriented architecture with monitoring|
|US20060031930 *||May 19, 2005||Feb 9, 2006||Bea Systems, Inc.||Dynamically configurable service oriented architecture|
|US20060034237 *||Sep 7, 2005||Feb 16, 2006||Bea Systems, Inc.||Dynamically configurable service oriented architecture|
|US20060037027 *||Oct 11, 2005||Feb 16, 2006||International Business Machines Corporation||Method and system for time synchronization among systems using parallel sysplex links|
|US20060069791 *||May 18, 2005||Mar 30, 2006||Bea Systems, Inc.||Service oriented architecture with interchangeable transport protocols|
|US20060075300 *||Sep 23, 2004||Apr 6, 2006||Mukherjee Shubhendu S||Vectoring process-kill errors to an application program|
|US20060075301 *||Sep 24, 2004||Apr 6, 2006||Tryggve Fossum||Converting merge buffer system-kill errors to process-kill errors|
|US20060080419 *||Sep 7, 2005||Apr 13, 2006||Bea Systems, Inc.||Reliable updating for a service oriented architecture|
|US20060117147 *||Nov 30, 2004||Jun 1, 2006||Blinick Stephen L||Managing multiprocessor operations|
|US20060161917 *||Jan 19, 2005||Jul 20, 2006||Leung Hin L||Performance in a virtualization architecture with a processor abstraction layer|
|US20060168479 *||Jan 25, 2005||Jul 27, 2006||Seagate Technology Llc||Real time event logging and analysis in a software system|
|US20060212593 *||May 20, 2005||Sep 21, 2006||Bea Systems, Inc.||Dynamic service composition and orchestration|
|US20060212763 *||Jul 18, 2005||Sep 21, 2006||Fujitsu Limited||Error notification method and information processing apparatus|
|US20070220332 *||Feb 13, 2006||Sep 20, 2007||Suresh Marisetty||Configurable error handling apparatus and methods to operate the same|
|US20080010506 *||Jul 17, 2007||Jan 10, 2008||Fujitsu Limited||Multi-CPU computer and method of restarting system|
|US20080034367 *||Oct 12, 2007||Feb 7, 2008||Bea Systems, Inc.||Message processing in a service oriented architecture|
|US20080168238 *||Mar 20, 2008||Jul 10, 2008||International Business Machines Corporation||Coordination of multiprocessor operations with shared resources|
|US20080229046 *||Mar 13, 2007||Sep 18, 2008||Microsoft Corporation||Unified support for solid state storage|
|US20080276131 *||Jul 22, 2008||Nov 6, 2008||International Business Machines Corporation||Systems and methods for event detection|
|US20090249031 *||Mar 18, 2009||Oct 1, 2009||Fujitsu Limited||Information processing apparatus and error processing|
|US20100125750 *||Nov 18, 2008||May 20, 2010||Moyer William C||Programmable error actions for a cache in a data processing system|
|US20110138219 *||Dec 8, 2009||Jun 9, 2011||Walton Andrew C||Handling errors in a data processing system|
|US20110161734 *||Jun 30, 2011||Ibm Corporation||Process integrity in a multiple processor system|
|US20120233498 *||Sep 13, 2012||Ravindraraj Ramaraju||Hierarchical error correction for large memories|
|DE112010004013T5||Dec 6, 2010||Nov 15, 2012||International Business Machines Corporation||Prozessintegritšt in einem Mehrprozessorsystem|
|WO2011080027A1||Dec 6, 2010||Jul 7, 2011||International Business Machines Corporation||Process integrity in a multiple processor system|
|WO2012121777A2 *||Dec 21, 2011||Sep 13, 2012||Intel Corporation||Error management across hardware and software layers|
|WO2012121777A3 *||Dec 21, 2011||Nov 8, 2012||Intel Corporation||Error management across hardware and software layers|
|U.S. Classification||714/10, 714/E11.023, 714/37|
|Cooperative Classification||G06F11/0793, G06F11/0724|
|European Classification||G06F11/07P1E1, G06F11/07P10|
|Apr 24, 2000||AS||Assignment|
Owner name: INTEL CORPORATION, CALIFORNIA
Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:MARISETTY, SURESH;AYYAR, MANI;QUACH, NHON T.;AND OTHERS;REEL/FRAME:010777/0590;SIGNING DATES FROM 20000211 TO 20000418
|Mar 9, 2007||FPAY||Fee payment|
Year of fee payment: 4
|Mar 10, 2011||FPAY||Fee payment|
Year of fee payment: 8
|Mar 4, 2015||FPAY||Fee payment|
Year of fee payment: 12